WisconsinAIVision/MixNMatch
Pytorch implementation of MixNMatch
Disentangles multiple visual factors (pose, shape, color, background) from images to enable fine-grained conditional image synthesis by mixing attributes from different sources. Uses a two-stage training pipeline with separate generator and encoder networks that learn to isolate and recombine these factors in both latent code and feature spaces. Supports both image-to-image manipulation and cross-domain style transfer (cartoon/sketch to realistic images) on fine-grained categories like birds, dogs, and cars.
971 stars. No commits in the last 6 months.
Stars
971
Forks
187
Language
Python
License
—
Category
Last pushed
Jul 07, 2020
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/WisconsinAIVision/MixNMatch"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
Westlake-AI/openmixup
CAIRI Supervised, Semi- and Self-Supervised Visual Representation Learning Toolbox and Benchmark
YU1ut/MixMatch-pytorch
Code for "MixMatch - A Holistic Approach to Semi-Supervised Learning"
kamata1729/QATM_pytorch
Pytorch Implementation of QATM:Quality-Aware Template Matching For Deep Learning
nttcslab/msm-mae
Masked Spectrogram Modeling using Masked Autoencoders for Learning General-purpose Audio Representations
rgeirhos/generalisation-humans-DNNs
Data, code & materials from the paper "Generalisation in humans and deep neural networks" (NeurIPS 2018)